Skip to main content
Skip to navigation

Sept. 4, 2014 Volume 36, No. 2

MU researchers develop software to more accurately analyze tweets

Alternate text

Sean Goggins, left, assistant professor in the School of Information Science and Learning Technologies, and doctoral student Ian Graves have developed software that might aid Twitter analysts. Photo courtesy of MU News Bureau.

The program could help analysts gain better insight on Twitter trends

Many media outlets run updates on “trending” topics on Twitter. Determining the trends tend to be based on hashtag analysis.

But perhaps there is a way to drill down for more precise information, which might help Twitter analysts gain insight into human behavior associated with trends and events.

Researchers at the University of Missouri have developed software that might aid the Twitter analysts. Their study, “Sifting signal from noise: A new perspective on the meaning of tweets about the ‘big game,’ ” was published in August in the journal New Media and Strategy.

Trending topics on Twitter show only the quantity of tweets associated with keywords and hashtags. They don’t offer qualitative information about the tweets themselves. “Trends on Twitter are almost always associated with hashtags, which only gives you part of the story,” said Sean Goggins, assistant professor in MU’s School of Information Science and Learning Technologies.

The research team developed a software program that analyzes event-based tweets and measures the context of tweets rather than simply the number of tweets. The tweets analyzed were on the 2013 World Series and 2014 Super Bowl.

Ian Graves, a doctoral student in the computer science and IT department at the College of Engineering at MU, developed software that analyzes tweets based on the words found within the tweets. By programming tags researchers felt would be associated with the Super Bowl and World Series, the software analyzed the words and their placement within the 140-character tweets.

“The software is able to detect more nuanced occurrences within the tweet, like action happening on the baseball field in between batters at the plate or plays in the game,” Graves said. “The program uses a computational approach to seek out not only a spike in [specific] hashtags or words but also what’s really happening on a micro level.”

Goggins said that using this method to analyze tweets on a local level could help officials involved with community safety or disaster relief to investigate the causes of human-caused catastrophic events, such as the Boston Marathon bombing in 2013. It might also help analyze the risk for future catastrophic events.

“If analysts are just looking at the volume of tweets, they’re not getting the insight they need about what’s truly happening or the whole picture,” Goggins said. “By focusing on the words within the tweet, we have the potential to find a truer signal inside of a very noisy environment.”

The research was funded by a grant from the National Science Foundation.